110 citations · 124 across the 5 of their papers we have counts for
5 papers
Commutative Lie Group VAE for Disentanglement Learning
Xinqi Zhu, Chang Xu, Dacheng Tao
We view disentanglement learning as discovering an underlying structure that equivariantly reflects the factorized variations shown in data. Traditionally, such a structure is fixe…
Where and What? Examining Interpretable Disentangled Representations
Xinqi Zhu, Chang Xu, Dacheng Tao
Capturing interpretable variations has long been one of the goals in disentanglement learning. However, unlike the independence assumption, interpretability has rarely been exploit…
Approximated Bilinear Modules for Temporal Modeling
Xinqi Zhu, Chang Xu, Langwen Hui +2
We consider two less-emphasized temporal properties of video: 1. Temporal cues are fine-grained; 2. Temporal modeling needs reasoning. To tackle both problems at once, we exploit a…
Learning Disentangled Representations with Latent Variation Predictability
Xinqi Zhu, Chang Xu, Dacheng Tao
Latent traversal is a popular approach to visualize the disentangled latent representations. Given a bunch of variations in a single unit of the latent representation, it is expect…
B-CNN: Branch Convolutional Neural Network for Hierarchical Classification
Xinqi Zhu, Michael Bain
Convolutional Neural Network (CNN) image classifiers are traditionally designed to have sequential convolutional layers with a single output layer. This is based on the assumption…